{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CXCKIEWAKVMBMXBA4AZIE6UAL2","short_pith_number":"pith:CXCKIEWA","schema_version":"1.0","canonical_sha256":"15c4a412c05558165c20e032827a805eafbb31823220ea7f31c32609fed4985f","source":{"kind":"arxiv","id":"2404.15700","version":2},"attestation_state":"computed","paper":{"title":"MAS-SAM: Segment Any Marine Animal with Aggregated Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Huchuan Lu, Pingping Zhang, Tianyu Yan, Xinhao Deng, Yang Liu, Zifu Wan","submitted_at":"2024-04-24T07:38:14Z","abstract_excerpt":"Recently, Segment Anything Model (SAM) shows exceptional performance in generating high-quality object masks and achieving zero-shot image segmentation. However, as a versatile vision model, SAM is primarily trained with large-scale natural light images. In underwater scenes, it exhibits substantial performance degradation due to the light scattering and absorption. Meanwhile, the simplicity of the SAM's decoder might lead to the loss of fine-grained object details. To address the above issues, we propose a novel feature learning framework named MAS-SAM for marine animal segmentation, which in"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2404.15700","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-24T07:38:14Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"3492ebd770d0fc874356eee4b303cff7428f2910ca0fecf07d91f2bfc1aedeee","abstract_canon_sha256":"c79acf67caa46e7d9cdc97210e869f7b13d255404c70b6dc74756af512609080"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:17:14.648414Z","signature_b64":"UzuGv4tlr9d20u7vdB/v/5pxxvYBZkLICzMP4LA11p8AVxTPxRjHocQC6AfvOKOX46nWF2M39oM/WaydGY1aAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15c4a412c05558165c20e032827a805eafbb31823220ea7f31c32609fed4985f","last_reissued_at":"2026-07-05T08:17:14.647946Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:17:14.647946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MAS-SAM: Segment Any Marine Animal with Aggregated Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Huchuan Lu, Pingping Zhang, Tianyu Yan, Xinhao Deng, Yang Liu, Zifu Wan","submitted_at":"2024-04-24T07:38:14Z","abstract_excerpt":"Recently, Segment Anything Model (SAM) shows exceptional performance in generating high-quality object masks and achieving zero-shot image segmentation. However, as a versatile vision model, SAM is primarily trained with large-scale natural light images. In underwater scenes, it exhibits substantial performance degradation due to the light scattering and absorption. Meanwhile, the simplicity of the SAM's decoder might lead to the loss of fine-grained object details. To address the above issues, we propose a novel feature learning framework named MAS-SAM for marine animal segmentation, which in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.15700","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2404.15700/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2404.15700","created_at":"2026-07-05T08:17:14.648000+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.15700v2","created_at":"2026-07-05T08:17:14.648000+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.15700","created_at":"2026-07-05T08:17:14.648000+00:00"},{"alias_kind":"pith_short_12","alias_value":"CXCKIEWAKVMB","created_at":"2026-07-05T08:17:14.648000+00:00"},{"alias_kind":"pith_short_16","alias_value":"CXCKIEWAKVMBMXBA","created_at":"2026-07-05T08:17:14.648000+00:00"},{"alias_kind":"pith_short_8","alias_value":"CXCKIEWA","created_at":"2026-07-05T08:17:14.648000+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08906","citing_title":"DifferSeg: Towards Diverse Multimodal Binary Segmentation via Differential Perception and Frequency Guidance","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25651","citing_title":"Hierarchical Consistency Learning for Test-time Adaptation in Camouflage Perception","ref_index":80,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CXCKIEWAKVMBMXBA4AZIE6UAL2","json":"https://pith.science/pith/CXCKIEWAKVMBMXBA4AZIE6UAL2.json","graph_json":"https://pith.science/api/pith-number/CXCKIEWAKVMBMXBA4AZIE6UAL2/graph.json","events_json":"https://pith.science/api/pith-number/CXCKIEWAKVMBMXBA4AZIE6UAL2/events.json","paper":"https://pith.science/paper/CXCKIEWA"},"agent_actions":{"view_html":"https://pith.science/pith/CXCKIEWAKVMBMXBA4AZIE6UAL2","download_json":"https://pith.science/pith/CXCKIEWAKVMBMXBA4AZIE6UAL2.json","view_paper":"https://pith.science/paper/CXCKIEWA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.15700&json=true","fetch_graph":"https://pith.science/api/pith-number/CXCKIEWAKVMBMXBA4AZIE6UAL2/graph.json","fetch_events":"https://pith.science/api/pith-number/CXCKIEWAKVMBMXBA4AZIE6UAL2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CXCKIEWAKVMBMXBA4AZIE6UAL2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CXCKIEWAKVMBMXBA4AZIE6UAL2/action/storage_attestation","attest_author":"https://pith.science/pith/CXCKIEWAKVMBMXBA4AZIE6UAL2/action/author_attestation","sign_citation":"https://pith.science/pith/CXCKIEWAKVMBMXBA4AZIE6UAL2/action/citation_signature","submit_replication":"https://pith.science/pith/CXCKIEWAKVMBMXBA4AZIE6UAL2/action/replication_record"}},"created_at":"2026-07-05T08:17:14.648000+00:00","updated_at":"2026-07-05T08:17:14.648000+00:00"}